Attributed Text Generation via Post-hoc Research and Revision

Authors:
  • LGLuyu Gao
    Luyu Gao
  • ZDZhuyun Dai
    Zhuyun Dai
  • PPPanupong Pasupat
    Panupong Pasupat
  • ACAnthony Chen
    Anthony Chen
  • ACArun Tejasvi Chaganty
    Arun Tejasvi Chaganty
  • YFYicheng Fan
    Yicheng Fan
  • VZVincent Y. Zhao
    Vincent Y. Zhao
  • NLNi Lao
    Ni Lao
  • HLHongrae Lee
    Hongrae Lee
  • DJDa-Cheng Juan
    Da-Cheng Juan
  • KGKelvin Guu
    Kelvin Guu

Abstract
Language models (LMs) now excel at many tasks such as few-shot learning, question answering, reasoning, and dialog. However, they sometimes generate unsupported or misleading content. A user cannot easily determine whether their outputs are trustworthy or not, because most LMs do not have any built-in mechanism for attribution to external evidence. To enable attribution while still preserving all the powerful advantages of recent generation models, we propose RARR (Retrofit Attribution using Research and Revision), a system that 1) automatically finds attribution for the output of any text generation model and 2) post-edits the output to fix unsupported content while preserving the original output as much as possible. When applied to the output of several state-of-the-art LMs on a diverse set of generation tasks, we find that RARR significantly improves attribution while otherwise preserving the original input to a much greater degree than previously explored edit models. Furthermore, the implementation of RARR requires only a handful of training examples, a large language model, and standard web search.